Data Engineering Intern at Capgemini Engineering

Developed a batch anomaly detection pipeline in Python using scikit-learn (Isolation Forest) to identify abnormal file size growth and data transfer slowdowns from customer event data; designed and implemented Splunk ingestion pipelines and SPL queries to process and analyze thousands of files per day; built operational and analytical Splunk dashboards to surface data quality issues and system performance trends for internal engineers and external clients; configured alerting workflows in Splunk to automatically flag anomalous patterns and performance degradation; independently owned the Splunk data engineering stack, delivering end-to-end observability solutions in a production consulting environment.